Options
2021
Journal Article
Titel
PTT-based contact-less blood pressure measurement using an RGB-camera
Abstract
Introduction Although blood pressure is one of the most fundamental vital parameters for evaluating the health status of a person, state-of-the-art measurement methods have noticeable limitations. Cuff-based systems are uncomfortable for patients, provide only intermitted measurements and have a comparatively high error margin. Continuous cuff-less measurement devices are mostly invasive and pose a high risk for infections or thrombosis. To overcome these limitations, we developed and tested a surrogate-based non-invasive blood pressure measurement method using an RGB-camera. Methods Our proposed method employs the relation between the pulse transit time (PTT) and blood pressure. Therefore, we start with a chromatic adaption to provide a constant illumination throughout the video. Then, we detect and track two skin regions, one in the face and the other one on the palm, to extract two remote photoplethysmography (rPPG) signals at different body locations with different distances from the heart. After denoising the signals, the zero crossings are detected and finally the PTT is calculated as the temporal delay of the zero crossings between these two regions. To establish the correlation between the PTT values and the blood pressure, different regression models are trained and evaluated. Results Tests were performed with eight subjects between the age of 18 and 62, where each subject was recorded three times for 30 seconds each. Before and after the recording, reference measurements were taken using a cuff-based sphygmomanometer. Since the phyiological parameters of the cardiac system are different for each person, an individual calibration is required to obtain the systolic and diastolic blood pressure from the PTT values. Conclusion The calibration results are limited by the small number of samples, however, the results show a strong correlation between the PTT values and the blood pressure. For the future, we are going to record videos with beat-to-beat reference data to enable a more effective training.
Author(s)